North Carolina General Statutes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint, so the description adds real value by disclosing the data's provenance (statutory dates from the legislature's record, not database observation timestamps) and the shape of the result (one entry per session law, grouped by year, plus first-enacted year and total count). This is exactly the kind of caveat that prevents misreading the output; only the fact that the output schema already covers result structure keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core answer, then usage examples, then the result shape, then the disambiguation clause. Every sentence carries information; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be enumerated, yet the description still characterizes them usefully. With a single fully documented parameter and explicit sibling routing, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

One parameter with 100% schema coverage, including examples ("14-33", "G.S. 20-141") and a description. The prose adds no format or syntax guidance beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope: statutory enactment and every amendment date for an NC statute section. The title/description pair makes clear this is the legislative history timeline, not the text itself, so it is distinguishable from siblings at a glance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete user-intent triggers ("how often has G.S. 14-33 changed", "when was this last amended") and explicitly routes away: recent_law_changes for database-observed text changes, get_statute or diff_statute for the wording itself. When-to-use and alternatives are both stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint=false, and the description adds real behavioral scoping on top: only section-level references count as edges, chapter-wide and "this Article" references are excluded, and INBOUND is flagged as the direction unavailable from reading a single statute. It does not describe the limit/cap behavior, but the safety and scope profile is well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core question, then examples, then scope caveats, then the sibling pointer — a sensible order with no filler. Slightly dense across four short blocks, but each sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a moderate-complexity lookup tool with an output schema (so return shape needn't be explained) and safety annotations, the description covers purpose, direction semantics, scope rules, and the alternative tool. The only material omission is the behavior of the limit parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (limit and direction have no schema descriptions), so the description must compensate. It does so for the most important parameter by defining OUTBOUND vs INBOUND conceptually, which implies the direction values, but it never clarifies what limit does or what its 100 default means.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource pair (a NC statute's outbound and inbound citations) and immediately separates the two directions, which is the core of what the tool does. It also distinguishes itself from get_statute, so an agent can route without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete trigger queries ("what does G.S. 14-72.1 depend on", "what else references it") and an explicit exclusion plus alternative: "For the text itself use get_statute." The when-to-use and when-not-to-use conditions are both present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds real behavioral context: the ingest-observation floor that causes 'most sections have only one version and return diff: null'. It doesn't cover the format modes or any cost/pagination behavior, but the key failure mode (null diffs) is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight blocks: purpose first, then the mode semantics, then the limitation and sibling routing. Every sentence carries distinct information; nothing is repeated from the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 params (1 required), an output schema present so return-shape explanation is unnecessary, and no annotations gap to fill, this description supplies what's missing: mode semantics, data-coverage limits, and sibling routing. The only residual hole (format options, date semantics) is minor for a diff tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description carries meaningful load for `mode`, explaining both enum-like values and their semantics; without this, the agent would have no way to know what 'pending' vs 'observed' means since the schema gives `mode` no description and no enum. However, `format`, `from_date`, and `to_date` remain unexplained in both the description and the schema (only coverage is on `citation`), so it doesn't fully compensate for the 20% coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+granularity: 'Word-level diff of a North Carolina (NC) statute section between two versions.' It further splits the operation into two named modes (pending vs observed), which is exactly the distinction an agent needs to pick this tool over get_statute or search_statutes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit selection criteria for each mode ('what will change on 1 October' vs recorded versions between two dates) and names the alternatives with their conditions: 'For earlier change dates use amendment_history; for pending text use pending_changes.' Both when-to-use and when-not-to-use are covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses that results are ranked sections with highlighted fragments rather than full text, that the tool searches law currently in force at section level, that court shorthand is case-insensitively expanded and reported back as `expanded_query`, and how to interpret a weak top rank. This is behaviorally rich context an agent cannot get from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage, return shape, and query syntax in that order; each paragraph carries a distinct piece of information. It is somewhat long and the shorthand-expansion behavior is stated twice (once here, once in the schema), which is mild redundancy rather than waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, yet the description still usefully characterizes the return shape for chaining into `get_statute`, and it covers the query syntax and empty-result interpretation an agent needs. The only real gap is the undocumented `chapter` and `include_repealed` filters, which limit the agent's ability to narrow or widen scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 25%, but the description thoroughly compensates for the required `query` parameter with phrase/-exclusion/`or` syntax and shorthand expansion. However, `chapter`, `limit` and `include_repealed` are documented nowhere; the text's "law in force today" hints at the default scope but never explains how to search repealed law or restrict to a chapter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Search) and resource (North Carolina statutes) with the scope of the search (topic, keyword or phrase). It explicitly names the sibling `get_statute` as the alternative when a citation is already known, so an agent can distinguish the two without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit when-to-use condition ("you know the SUBJECT but not the citation") with three concrete example queries, and an explicit when-not-to-use rule pointing to `get_statute`. It even pre-empts the empty-result case by telling the agent that a low top rank means no statute is on point.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.